Cloud seeding is used to increase precipitation by dispersing substances (silver

Question

Cloud seeding is used to increase precipitation by dispersing substances (silver iodide, dry ice, table salt) into the air that serve as cloud condensation. Simpson (1975, Technometrics) reported the results on 26 seeded and 26 unseeded clouds in order of the amount of rainfall (in acre-feet), largest amount first. Here are 2 possible tests to study the question of whether cloud seeding work: Paired t-Test of mu(Seeded-Unseeded) T-Test of H_0: mu(Seeded-Unseeded) = 0 against H_A: mu(Seeded-Unseeded) > 0 t-Statistics = 3.64 with 25 df P-Value = 0.0006 2-SampZTest of mu(Seeded)-mu(Unseeded) H_0: mu(Seeded) - mu(Unseeded)=0 against H_A: mu(Seeded) - mu(Unseeded) >0 z-Statistics = 1.9953 bar x_seeded - bar x_unseeded = 277.1 P- Value = 0.0230 a. Which of these 2 tests is appropriate for these data? Explain. b. Using the test you selected in part (a) and a = 0.01, state your conclusion in context of the problem.

Explanation / Answer

a. COnditions for using Z - test

(i) Populations are normal - yes

(ii) samples happen to be large - no / may be yes

(iii) Population variances are known - no

(iv) Ha May be one sided and two sided.- yes

Conditions for using t- test for paired data

(i) samples happen to be small - yes

(ii) variances of the population need not to be known - yes

(b) Here alpha = 0.01 so we can reject the null hypothesis as P - value ( 0.0006) is less than the significance level alpha = 0.01. We can reject the null hypothesis and can say that precipitation has been increased due to cloud seeding.

(iii) Populations are normal - yes

(iv) Ha may be one sided or two sided - yes

And the most important point here is paired has been drawn based on amount of rainfall, largest amount first that means paired data is created and then t- statistic has been achieved.

Related Questions

Navigate

• Browse (All)
• Browse C
• Subjects

---

---

Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.